English

Natural Language to Code Using Transformers

Computation and Language 2022-02-02 v1 Machine Learning

Abstract

We tackle the problem of generating code snippets from natural language descriptions using the CoNaLa dataset. We use the self-attention based transformer architecture and show that it performs better than recurrent attention-based encoder decoder. Furthermore, we develop a modified form of back translation and use cycle consistent losses to train the model in an end-to-end fashion. We achieve a BLEU score of 16.99 beating the previously reported baseline of the CoNaLa challenge.

Keywords

Cite

@article{arxiv.2202.00367,
  title  = {Natural Language to Code Using Transformers},
  author = {Uday Kusupati and Venkata Ravi Teja Ailavarapu},
  journal= {arXiv preprint arXiv:2202.00367},
  year   = {2022}
}
R2 v1 2026-06-24T09:12:59.724Z